Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Update GPU compute capability check to reflect devices that are known to work correctly. #114

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 8 additions & 2 deletions run_alphafold.py
Original file line number Diff line number Diff line change
Expand Up @@ -628,10 +628,16 @@ def main(_):
if _RUN_INFERENCE.value:
# Fail early on incompatible devices, but only if we're running inference.
gpu_devices = jax.local_devices(backend='gpu')
if gpu_devices and float(gpu_devices[0].compute_capability) < 8.0:
compute_capability = float(gpu_devices[0].compute_capability)
if gpu_devices and (
compute_capability < 6.0
or (compute_capability >= 7.0 and compute_capability < 8.0)
):
raise ValueError(
'There are currently known unresolved numerical issues with using'
' devices with compute capability less than 8.0. See '
' devices with compute capability 7.x. The code has not been tested'
' with compute capability < 6.0. The code has been confirmed to work'
' with compute capability 6.x and 8.x. See '
' https://github.com/google-deepmind/alphafold3/issues/59 for'
' tracking.'
)
Expand Down